aeon-skill-evals
Validate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL).
Install / Use
npx skills add BankrBot/skills --skill aeon-skill-evalsInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of aeon-skill-evals
aeon-skill-evals scores 83/100 on our quality scale, 3163rd of 4,700 Development & Engineering skills we index.
Its SKILL.md is 2.6 KB long, split into 6 sections with 1 code example: a solid amount of guidance for an agent.
With 1,201 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so aeon-skill-evals is actively maintained.
- Our last check on 2026-11-07 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
aeon-skill-evals compared with similar skills
All 4 of these similar skills score higher than aeon-skill-evals; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| aeon-skill-evals (this skill)by BankrBot | 83 | 1.2k | 54d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install aeon-skill-evals?
- Run
npx skills add BankrBot/skills --skill aeon-skill-evals. The install tabs above show the steps for each supported agent. - Which AI agents does aeon-skill-evals work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is aeon-skill-evals safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is aeon-skill-evals still maintained?
- The repository was last updated about 2 months ago, so aeon-skill-evals is actively maintained.
Skill content
View source on GitHubname: aeon-skill-evals description: | Validate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL). Bootstrap mode generates a starter manifest from a skill's recent successful runs so manifests aren't written speculatively. Triggers: "evaluate this skill's output", "check skill X for regressions", "bootstrap evals for Y", "did this skill output pass quality gates".
aeon-skill-evals
Quality net for installed skills. Each skill can declare an assertion manifest; outputs are checked against it; failing assertions surface regressions and route concrete fixes.
Manifest format
token-movers:
min_words: 200
required_patterns: ["Top movers", "24h"]
forbidden_patterns: ["I cannot", "as an AI"]
must_cite_source: true
min_distinct_items: 5
narrative-tracker:
min_words: 400
required_sections: ["TRANSITIONS", "POSITIONS", "MAP"]
forbidden_patterns: ["exciting", "consider"]
must_have_position_call: true
Supported assertions: min_words / max_words, required_patterns / forbidden_patterns, required_sections, must_cite_source, min_distinct_items, output_pattern (regex), and per-skill-family custom binary checks.
Operations
eval— run every manifest-defined skill against its latest output.eval --skill=NAME— one skill.bootstrap --skill=NAME— generate a starter manifest from recent successful runs.
Regression states
| State | Action |
|---|---|
| NEW_FAIL | Passing last run, failing now. Severity scales with pass streak. |
| NEW_PASS | Failing last run, passing now. Log the win. |
| CHRONIC | Failing > 3 consecutive runs. Recommend operator review. |
| STABLE_FAIL | Always failing. Manifest assertion mismatch — flag for review. |
State in local evals-state.json.
Bootstrap mode
Samples last 5 successful runs of a skill. Computes:
min_wordsat p25 of historical runs.- Required patterns from common section headers.
- Forbidden patterns from default list (refusals, hedging filler).
Emits the proposed manifest for review. Never auto-commits — assertions need a human signoff.
Rules
- Assertions are observations, not specifications. Bootstrap before writing speculatively.
- Forbidden patterns catch hallucination markers and refusals. Keep the list tight; don't lint stylistic choices.
- Chronic failures get a recommendation, not a re-file.
- Manifest changes are reviewed; never auto-edited by this skill.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
